chore(model gallery): add textsynth-8b-i1 (#5076)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-26 14:40:19 +01:00 committed by GitHub
parent 7fa159e164
commit c069e61b26
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -7272,6 +7272,22 @@
- filename: jdineen_Llama-3.1-8B-Think-Q4_K_M.gguf
sha256: 47efe28c37f12a644e02abb417c421b243e8001d3c9345dd7f650c8050ab78fc
uri: huggingface://bartowski/jdineen_Llama-3.1-8B-Think-GGUF/jdineen_Llama-3.1-8B-Think-Q4_K_M.gguf
- !!merge <<: *llama31
name: "textsynth-8b-i1"
urls:
- https://huggingface.co/theprint/TextSynth-8B
- https://huggingface.co/mradermacher/TextSynth-8B-i1-GGUF
description: |
This is a finetune of Llama 3.1 8B, trained on synthesizing text from two different sources. When used for other purposes, the result is a slightly more creative version of Llama 3.1, using more descriptive and evocative language in some instances.
It's great for brainstorming sessions, creative writing and free-flowing conversations. It's less good for technical documentation, email writing and that sort of thing.
overrides:
parameters:
model: TextSynth-8B.i1-Q4_K_M.gguf
files:
- filename: TextSynth-8B.i1-Q4_K_M.gguf
sha256: 9186a8cb3a797cd2cd5b2eeaee99808674d96731824a9ee45685bbf480ba56c3
uri: huggingface://mradermacher/TextSynth-8B-i1-GGUF/TextSynth-8B.i1-Q4_K_M.gguf
- !!merge <<: *llama33
name: "llama-3.3-magicalgirl-2.5-i1"
icon: https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/FGK0qBGmELj6DEUxbbrdR.png